Transformers

Reframing Image Difference Captioning with BLIP2IDC and Synthetic Augmentation WACV 2025 Region-aware Anchoring Mechanism for Efficient Referring Visual Grounding ICCV 2025 Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation ACL 2025 ReGLA: Refining Gated Linear Attention NAACL 2025 Reinforced Learning Explicit Circuit Representations for Quantum State Characterization from Local Measurements ICML 2025 RelitLRM: Generative Relightable Radiance for Large Reconstruction Models ICLR 2025 REMEDY: Recipe Merging Dynamics in Large Vision-Language Models ICLR 2025 Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios CVPR 2025 ReMP: Reusable Motion Prior for Multi-Domain 3D Human Pose Estimation and Motion Inbetweening WACV 2025 REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers ICCV 2025 RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers ICML 2025 Replacing Paths with Connection-Biased Attention for Knowledge Graph Completion AAAI 2025 RepLoRA: Reparameterizing Low-rank Adaptation via the Perspective of Mixture of Experts ICML 2025 Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think ICLR 2025 Representing Rule-based Chatbots with Transformers NAACL 2025 Residual Matrix Transformers: Scaling the Size of the Residual Stream ICML 2025 ResidualViT for Efficient Temporally Dense Video Encoding ICCV 2025 Resolving Packets from Counters: Enabling Multi-scale Network Traffic Super Resolution via Composable Large Traffic Model NSDI 2025 Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning ICCV 2025 Restoring Missing Spaces in Scraped Hebrew Social Media NAACL 2025 Rethinking Decoder Design: Improving Biomarker Segmentation Using Depth-to-Space Restoration and Residual Linear Attention CVPR 2025 Rethinking Layered Graphic Design Generation with a Top-Down Approach ICCV 2025 Rethinking Leveraging Pre-Trained Multi-Layer Representations for Speaker Verification Interspeech 2025 Rethinking Spiking Self-Attention Mechanism: Implementing a-XNOR Similarity Calculation in Spiking Transformers CVPR 2025 Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction CVPR 2025